revset: support raw string literals

This adds support for r'...' and r"..." as string literals. Strings
with the "r" prefix will not have their escape characters interpreted.

This is especially useful for grep(), where, with regular string
literals, \number is interpreted as an octal escape code, and \b is
interpreted as the backspace character (\x08).

mercurial/help/revsets.txt

@@ -7,8 +7,11 operators. Parenthesis can be used for g
 Identifiers such as branch names must be quoted with single or double
 quotes if they contain characters outside of
 ``[._a-zA-Z0-9\x80-\xff]`` or if they match one of the predefined
-predicates. Special characters can be used in quoted identifiers by
-escaping them, e.g., ``\n`` is interpreted as a newline.
+predicates.
+
+Special characters can be used in quoted identifiers by escaping them,
+e.g., ``\n`` is interpreted as a newline. To prevent them from being
+interpreted, strings can be prefixed with ``r``, e.g. ``r'...'``.
 
 There is a single prefix operator:
 
@@ -82,7 +85,8 The following predicates are supported:
   An alias for ``::.`` (ancestors of the working copy's first parent).
 
 ``grep(regex)``
-  Like ``keyword(string)`` but accepts a regex.
+  Like ``keyword(string)`` but accepts a regex. Use ``grep(r'...')``
+  to ensure special escape characters are handled correctly.
 
 ``head()``
   Changeset is a head.

mercurial/revset.py

@@ -48,7 +48,14 def tokenize(program):
             pos += 1 # skip ahead
         elif c in "():,-|&+!": # handle simple operators
             yield (c, None, pos)
-        elif c in '"\'': # handle quoted strings
+        elif (c in '"\'' or c == 'r' and
+              program[pos:pos + 2] in ("r'", 'r"')): # handle quoted strings
+            if c == 'r':
+                pos += 1
+                c = program[pos]
+                decode = lambda x: x
+            else:
+                decode = lambda x: x.decode('string-escape')
             pos += 1
             s = pos
             while pos < l: # find closing quote
@@ -57,7 +64,7 def tokenize(program):
                     pos += 2
                     continue
                 if d == c:
-                    yield ('string', program[s:pos].decode('string-escape'), s)
+                    yield ('string', decode(program[s:pos]), s)
                     break
                 pos += 1
             else:

tests/test-revset.t

@@ -215,6 +215,14 quoting needed
   ('func', ('symbol', 'grep'), ('string', '('))
   hg: parse error: invalid match pattern: unbalanced parenthesis
   [255]
+  $ try 'grep("\bissue\d+")'
+  ('func', ('symbol', 'grep'), ('string', '\x08issue\\d+'))
+  $ try 'grep(r"\bissue\d+")'
+  ('func', ('symbol', 'grep'), ('string', '\\bissue\\d+'))
+  6
+  $ try 'grep(r"\")'
+  hg: parse error at 7: unterminated string
+  [255]
   $ log 'head()'
   0
   1